Online Video Deblurring via Dynamic Temporal Blending Networkopen access
- Authors
- Kim, Tae Hyun; Lee, Kyoung Mu; Scholkopf, Bernhard; Hirsch, Michael
- Issue Date
- Oct-2017
- Publisher
- IEEE
- Citation
- Proceedings of the IEEE International Conference on Computer Vision, pp.1 - 8
- Indexed
- OTHER
- Journal Title
- Proceedings of the IEEE International Conference on Computer Vision
- Start Page
- 1
- End Page
- 8
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/151423
- DOI
- 10.1109/ICCV.2017.435
- Abstract
- State-of-the-art video deblurring methods are capable of removing non-uniform blur caused by unwanted camera shake and/or object motion in dynamic scenes. However, most existing methods are based on batch processing and thus need access to all recorded frames, rendering them computationally demanding and time-consuming and thus limiting their practical use. In contrast, we propose an online (sequential) video deblurring method based on a spatio-temporal recurrent network that allows for realtime performance. In particular, we introduce a novel architecture which extends the receptive field while keeping the overall size of the network small to enable fast execution. In doing so, our network is able to remove even large blur caused by strong camera shake and/or fast moving objects. Furthermore, we propose a novel network layer that enforces temporal consistency between consecutive frames by dynamic temporal blending which compares and adaptively (at test time) shares features obtained at different time steps. We show the superiority of the proposed method in an extensive experimental evaluation.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 컴퓨터소프트웨어학부 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/151423)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.